ML Data & Eval Engineer, Siri Agent Modeling

Apple • Cupertino, CA

8d

About The Position

Apple’s Siri team is building the next generation of agents and deploying them at large customer scale. The ML Data & Eval Engineer is a generalist engineering role spanning the machine-learning lifecycle, with end-to-end ownership of the data and infrastructure behind frontier on-device machine learning, from raw data to Apple silicon. The engineer works closely with Siri on-device modeling, evaluation, and deployment teams, as well as Apple ML platform, compute, framework, and privacy partners. Responsibilities include designing, building, deploying, and maintaining systems that turn data into trained, evaluated, and deployable on-device models.

The role includes building scalable pipelines to curate, filter, deduplicate, augment, and version data for LLMs and agents, including fine-tuning sets, preference data, tool-use trajectories, evaluation sets, and synthetic data. It also involves building large-scale evaluation systems for agentic models, including sandboxed environments for tool use and multi-step tasks; creating model conversion, compression, quantization, benchmarking, and regression-tracking workflows for Apple silicon; improving bottlenecks across data loading, experiment tracking, and artifact management; and developing data quality, lineage, and governance tooling consistent with Apple’s privacy principles. The team values velocity, pragmatism, measurement, and shipping.

Requirements

• Strong computer science background in algorithms, data structures, and distributed systems design.
• Strong proficiency in Python.
• Hands-on experience with Docker, Kubernetes, and cloud infrastructure.
• Experience building large-scale data processing pipelines, such as Spark or Ray, or distributed ML infrastructure.
• Familiarity with the ML model lifecycle, including training, evaluation, and deployment, and frameworks such as PyTorch or JAX.
• Experience building, deploying, and debugging production services and data products end to end.
• Experience with agentic AI-assisted coding.
• Bachelor’s degree in Computer Science, Engineering, or a related discipline, or equivalent industry experience.
• At least 4 years of industry experience building production data or ML infrastructure.

Nice To Haves

• Experience building LLM data pipelines, such as synthetic data generation, LLM-as-judge filtering, or evaluation sets.
• Experience with workflow orchestrators such as Airflow, Kubeflow, or Argo.
• Experience with model conversion and optimization for on-device or edge deployment, such as Core ML, quantization, or pruning.
• Experience with data quality, lineage, and dataset versioning tools, and privacy-preserving data practices.
• Experience building tools and services that optimize ML systems beyond model selection.
• Collaborative approach and experience driving large cross-team projects.

Responsibilities

• Build scalable pipelines to curate, filter, deduplicate, augment, and version data for LLMs and agents.
• Develop data products such as fine-tuning sets, preference data, tool-use trajectories, evaluation sets, and synthetic data.
• Build systems for running large evaluation suites for agentic models, including sandboxed environments for tool use and multi-step tasks.
• Create pipelines for model conversion, compression, and quantization, and for on-device benchmarking and regression tracking on Apple silicon.
• Identify and remove bottlenecks across the ML lifecycle, including data loading, experiment tracking, and artifact management.
• Build data quality checks, lineage, and governance tooling to keep datasets and models trustworthy and consistent with Apple’s privacy principles.
• Own services and data products through conception, design, implementation, deployment, and maintenance.
• Collaborate with Siri modeling, evaluation, and deployment teams and Apple ML platform, compute, framework, and privacy partners.
• Drive large cross-team projects.

What This Job Offers

• Job Type: Full-time
• Career Level: Mid Level